Triple

T20702403
Position Surface form Disambiguated ID Type / Status
Subject American Fiction E508815 entity
Predicate editedBy P1954 FINISHED
Object Hilda Rasula
Hilda Rasula is an editor and literary professional known for her work on the journal American Fiction.
E1445227 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Hilda Rasula | Statement: [American Fiction, editedBy, Hilda Rasula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hilda Rasula
Context triple: [American Fiction, editedBy, Hilda Rasula]
  • A. Rosita Farisi
    Rosita Farisi is a Victorian-era companion-like character who assists the Doctor in the 2008 "Doctor Who" Christmas special "The Next Doctor."
  • B. Gloria Akalitus
    Gloria Akalitus is a strict, bureaucratic hospital administrator and recurring character on the television series "Nurse Jackie."
  • C. Hilda Patricia Marroquín
    Hilda Patricia Marroquín is a Guatemalan public figure who served as First Lady of Guatemala during the presidency of her husband, Jimmy Morales.
  • D. Marlene Mathias
    Marlene Mathias is known as the daughter of American Olympic decathlon champion and politician Bob Mathias.
  • E. Hazel Poa
    Hazel Poa is a Singaporean politician and former civil servant known for her leadership roles in opposition parties such as the National Solidarity Party and the Progress Singapore Party.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Hilda Rasula
Triple: [American Fiction, editedBy, Hilda Rasula]
Generated description
Hilda Rasula is an editor and literary professional known for her work on the journal American Fiction.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hilda Rasula
Target entity description: Hilda Rasula is an editor and literary professional known for her work on the journal American Fiction.
  • A. Rosita Farisi
    Rosita Farisi is a Victorian-era companion-like character who assists the Doctor in the 2008 "Doctor Who" Christmas special "The Next Doctor."
  • B. Gloria Akalitus
    Gloria Akalitus is a strict, bureaucratic hospital administrator and recurring character on the television series "Nurse Jackie."
  • C. Hilda Patricia Marroquín
    Hilda Patricia Marroquín is a Guatemalan public figure who served as First Lady of Guatemala during the presidency of her husband, Jimmy Morales.
  • D. Marlene Mathias
    Marlene Mathias is known as the daughter of American Olympic decathlon champion and politician Bob Mathias.
  • E. Hazel Poa
    Hazel Poa is a Singaporean politician and former civil servant known for her leadership roles in opposition parties such as the National Solidarity Party and the Progress Singapore Party.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e0b4c2b2a481909e31e9cb8f81ab55 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6c18cb9cc819095d0669dca037424 completed April 21, 2026, 12:15 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08d7f035f4819088fd2f0563a3ebda completed May 16, 2026, 8:47 p.m.
NEDg Description generation batch_6a08d8aa839c81908be2c3e5c8f54ef5 completed May 16, 2026, 8:50 p.m.
NED2 Entity disambiguation (via description) batch_6a08d9784a08819080de2a65fc129e94 completed May 16, 2026, 8:54 p.m.
Created at: April 16, 2026, 12:12 p.m.